ambitious-problem-solving pushes a task past literal compliance by raising ambition, deepening evidence and adversarial validation, and borrowing methods across disciplines.
alexferrari88/skills
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 10
- GitHub stars
- 2
- GitHub forks
- 0
Install with an AI assistant
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/alexferrari88/skills.Loading the repository README…
Posts
See all →Skills in this repository
Showing 10 of 10 collected skills.
Extract full content from webpages, articles, PDFs, and JavaScript-heavy URLs through self-hosted Firecrawl with automatic Crawl4AI fallback. Use when ordinary built-in web fetching fails, is incomplete, or when the user asks for full page extraction. Do not…
Use this skill to elevate a task, prompt, plan, analysis, or workflow across altitude (outcomes and autonomous loops over one-off artifacts), depth (raw data, expert instruments, adversarial testing, and external verification over surface summaries), and…
Use this skill to design, audit, or troubleshoot high-efficiency learning for hierarchical skills, especially mathematics, technical subjects, tutoring flows, study plans, curricula, assessments, and adaptive learning systems. Activate when deciding what a…
Use when a user wants to learn by examining, defending, or stress-testing a concrete argument through guided dialogue.
Use Antigravity CLI (`agy`) to run agent sessions, non-interactive prompts, model discovery, project/workspace selection, plugin management, CLI install/update checks, changelog inspection, and conversation resume workflows. Trigger when the user asks to use…
Evidence-backed tutoring runtime for teaching a user a new skill or concept within a stateful learning workspace.
Automating Android tasks, profiles, scenes, and actions using Tasker. Use this skill when the user wants to design, modify, or debug Tasker configurations, write JavaScriptlets or shell scripts for Tasker, handle Android intents, or use Tasker variables and…
Reuse Hermes Agent's active runtime provider and credentials inside DSPy programs, including Predict, ChainOfThought, and RLM, without duplicating API keys. Designed to be provider-aware and shareable across Hermes installations.
Use DSPy.RLM with Hermes runtime auth for long-context tasks that need programmatic decomposition, recursive sub-calls, and dense access across large prompts, corpora, or codebases.
Hermes-native deep research protocol for multi-source synthesis, verification, parallel subresearch, and decision-grade reporting using web_search, web_extract, browser fallback, delegate_task, and Python-backed scoring.